Feasibility of Deep Learning Algorithms for Binary Classification Problems (이진 분류문제에서의 딥러닝 알고리즘의 활용 가능성 평가)
-
- Journal of Intelligence and Information Systems
- /
- v.23 no.1
- /
- pp.95-108
- /
- 2017
Recently, AlphaGo which is Bakuk (Go) artificial intelligence program by Google DeepMind, had a huge victory against Lee Sedol. Many people thought that machines would not be able to win a man in Go games because the number of paths to make a one move is more than the number of atoms in the universe unlike chess, but the result was the opposite to what people predicted. After the match, artificial intelligence technology was focused as a core technology of the fourth industrial revolution and attracted attentions from various application domains. Especially, deep learning technique have been attracted as a core artificial intelligence technology used in the AlphaGo algorithm. The deep learning technique is already being applied to many problems. Especially, it shows good performance in image recognition field. In addition, it shows good performance in high dimensional data area such as voice, image and natural language, which was difficult to get good performance using existing machine learning techniques. However, in contrast, it is difficult to find deep leaning researches on traditional business data and structured data analysis. In this study, we tried to find out whether the deep learning techniques have been studied so far can be used not only for the recognition of high dimensional data but also for the binary classification problem of traditional business data analysis such as customer churn analysis, marketing response prediction, and default prediction. And we compare the performance of the deep learning techniques with that of traditional artificial neural network models. The experimental data in the paper is the telemarketing response data of a bank in Portugal. It has input variables such as age, occupation, loan status, and the number of previous telemarketing and has a binary target variable that records whether the customer intends to open an account or not. In this study, to evaluate the possibility of utilization of deep learning algorithms and techniques in binary classification problem, we compared the performance of various models using CNN, LSTM algorithm and dropout, which are widely used algorithms and techniques in deep learning, with that of MLP models which is a traditional artificial neural network model. However, since all the network design alternatives can not be tested due to the nature of the artificial neural network, the experiment was conducted based on restricted settings on the number of hidden layers, the number of neurons in the hidden layer, the number of output data (filters), and the application conditions of the dropout technique. The F1 Score was used to evaluate the performance of models to show how well the models work to classify the interesting class instead of the overall accuracy. The detail methods for applying each deep learning technique in the experiment is as follows. The CNN algorithm is a method that reads adjacent values from a specific value and recognizes the features, but it does not matter how close the distance of each business data field is because each field is usually independent. In this experiment, we set the filter size of the CNN algorithm as the number of fields to learn the whole characteristics of the data at once, and added a hidden layer to make decision based on the additional features. For the model having two LSTM layers, the input direction of the second layer is put in reversed position with first layer in order to reduce the influence from the position of each field. In the case of the dropout technique, we set the neurons to disappear with a probability of 0.5 for each hidden layer. The experimental results show that the predicted model with the highest F1 score was the CNN model using the dropout technique, and the next best model was the MLP model with two hidden layers using the dropout technique. In this study, we were able to get some findings as the experiment had proceeded. First, models using dropout techniques have a slightly more conservative prediction than those without dropout techniques, and it generally shows better performance in classification. Second, CNN models show better classification performance than MLP models. This is interesting because it has shown good performance in binary classification problems which it rarely have been applied to, as well as in the fields where it's effectiveness has been proven. Third, the LSTM algorithm seems to be unsuitable for binary classification problems because the training time is too long compared to the performance improvement. From these results, we can confirm that some of the deep learning algorithms can be applied to solve business binary classification problems.
This study was conducted to identify the correlation of bacterial phytase (
The job classification system of major job sites differs from site to site and is different from the job classification system of the 'SQF(Sectoral Qualifications Framework)' proposed by the SW field. Therefore, a new job classification system is needed for SW companies, SW job seekers, and job sites to understand. The purpose of this study is to establish a standard job classification system that reflects market demand by analyzing SQF based on job offer information of major job sites and the NCS(National Competency Standards). For this purpose, the association analysis between occupations of major job sites is conducted and the association rule between SQF and occupation is conducted to derive the association rule between occupations. Using this association rule, we proposed an intelligent job classification system based on data mapping the job classification system of major job sites and SQF and job classification system. First, major job sites are selected to obtain information on the job classification system of the SW market. Then We identify ways to collect job information from each site and collect data through open API. Focusing on the relationship between the data, filtering only the job information posted on each job site at the same time, other job information is deleted. Next, we will map the job classification system between job sites using the association rules derived from the association analysis. We will complete the mapping between these market segments, discuss with the experts, further map the SQF, and finally propose a new job classification system. As a result, more than 30,000 job listings were collected in XML format using open API in 'WORKNET,' 'JOBKOREA,' and 'saramin', which are the main job sites in Korea. After filtering out about 900 job postings simultaneously posted on multiple job sites, 800 association rules were derived by applying the Apriori algorithm, which is a frequent pattern mining. Based on 800 related rules, the job classification system of WORKNET, JOBKOREA, and saramin and the SQF job classification system were mapped and classified into 1st and 4th stages. In the new job taxonomy, the first primary class, IT consulting, computer system, network, and security related job system, consisted of three secondary classifications, five tertiary classifications, and five fourth classifications. The second primary classification, the database and the job system related to system operation, consisted of three secondary classifications, three tertiary classifications, and four fourth classifications. The third primary category, Web Planning, Web Programming, Web Design, and Game, was composed of four secondary classifications, nine tertiary classifications, and two fourth classifications. The last primary classification, job systems related to ICT management, computer and communication engineering technology, consisted of three secondary classifications and six tertiary classifications. In particular, the new job classification system has a relatively flexible stage of classification, unlike other existing classification systems. WORKNET divides jobs into third categories, JOBKOREA divides jobs into second categories, and the subdivided jobs into keywords. saramin divided the job into the second classification, and the subdivided the job into keyword form. The newly proposed standard job classification system accepts some keyword-based jobs, and treats some product names as jobs. In the classification system, not only are jobs suspended in the second classification, but there are also jobs that are subdivided into the fourth classification. This reflected the idea that not all jobs could be broken down into the same steps. We also proposed a combination of rules and experts' opinions from market data collected and conducted associative analysis. Therefore, the newly proposed job classification system can be regarded as a data-based intelligent job classification system that reflects the market demand, unlike the existing job classification system. This study is meaningful in that it suggests a new job classification system that reflects market demand by attempting mapping between occupations based on data through the association analysis between occupations rather than intuition of some experts. However, this study has a limitation in that it cannot fully reflect the market demand that changes over time because the data collection point is temporary. As market demands change over time, including seasonal factors and major corporate public recruitment timings, continuous data monitoring and repeated experiments are needed to achieve more accurate matching. The results of this study can be used to suggest the direction of improvement of SQF in the SW industry in the future, and it is expected to be transferred to other industries with the experience of success in the SW industry.
This study uses corporate data from 2012 to 2018 when K-IFRS was applied in earnest to predict default risks. The data used in the analysis totaled 10,545 rows, consisting of 160 columns including 38 in the statement of financial position, 26 in the statement of comprehensive income, 11 in the statement of cash flows, and 76 in the index of financial ratios. Unlike most previous prior studies used the default event as the basis for learning about default risk, this study calculated default risk using the market capitalization and stock price volatility of each company based on the Merton model. Through this, it was able to solve the problem of data imbalance due to the scarcity of default events, which had been pointed out as the limitation of the existing methodology, and the problem of reflecting the difference in default risk that exists within ordinary companies. Because learning was conducted only by using corporate information available to unlisted companies, default risks of unlisted companies without stock price information can be appropriately derived. Through this, it can provide stable default risk assessment services to unlisted companies that are difficult to determine proper default risk with traditional credit rating models such as small and medium-sized companies and startups. Although there has been an active study of predicting corporate default risks using machine learning recently, model bias issues exist because most studies are making predictions based on a single model. Stable and reliable valuation methodology is required for the calculation of default risk, given that the entity's default risk information is very widely utilized in the market and the sensitivity to the difference in default risk is high. Also, Strict standards are also required for methods of calculation. The credit rating method stipulated by the Financial Services Commission in the Financial Investment Regulations calls for the preparation of evaluation methods, including verification of the adequacy of evaluation methods, in consideration of past statistical data and experiences on credit ratings and changes in future market conditions. This study allowed the reduction of individual models' bias by utilizing stacking ensemble techniques that synthesize various machine learning models. This allows us to capture complex nonlinear relationships between default risk and various corporate information and maximize the advantages of machine learning-based default risk prediction models that take less time to calculate. To calculate forecasts by sub model to be used as input data for the Stacking Ensemble model, training data were divided into seven pieces, and sub-models were trained in a divided set to produce forecasts. To compare the predictive power of the Stacking Ensemble model, Random Forest, MLP, and CNN models were trained with full training data, then the predictive power of each model was verified on the test set. The analysis showed that the Stacking Ensemble model exceeded the predictive power of the Random Forest model, which had the best performance on a single model. Next, to check for statistically significant differences between the Stacking Ensemble model and the forecasts for each individual model, the Pair between the Stacking Ensemble model and each individual model was constructed. Because the results of the Shapiro-wilk normality test also showed that all Pair did not follow normality, Using the nonparametric method wilcoxon rank sum test, we checked whether the two model forecasts that make up the Pair showed statistically significant differences. The analysis showed that the forecasts of the Staging Ensemble model showed statistically significant differences from those of the MLP model and CNN model. In addition, this study can provide a methodology that allows existing credit rating agencies to apply machine learning-based bankruptcy risk prediction methodologies, given that traditional credit rating models can also be reflected as sub-models to calculate the final default probability. Also, the Stacking Ensemble techniques proposed in this study can help design to meet the requirements of the Financial Investment Business Regulations through the combination of various sub-models. We hope that this research will be used as a resource to increase practical use by overcoming and improving the limitations of existing machine learning-based models.
This research is a case study to make sure the enhancement of students' imagination and creativity through developing and applying the Literature-Art-Science Integrated Education Program. Its research object was totally 25 persons of 29 students of the 1st to the 4 th Grades from Gunsan Sulsan Elementary School. Its research period lasted for 4 months from September to December, 2017, and I, as the research place, used the art room at Gunsan Sulsan Elementary School. The programs were totally 10 sessions with a unit of 1 session per each grade for 2 hours from 1:00 to 3:00 in the afternoon from Monday through Friday. I fixed ten themes of this program-eight plane modeling, and two solid modeling, and finished the work of storytelling during summer vacation. And I arranged their levels as low:middle:high(3:5:2) ones. The former was 'A Film of Monster Gorilla'(L), 'Learning the Spirit of Gyeongju Choi's Family'(M), 'A Tale of My Friend Made of Natural Materials'(L), 'The Reading of My Dream'(M), 'Gathering the Objects in My Mobile'(M), 'A Mock Trial of Marrying Off'(M), 'Painting My Favorite Children's Poem'(H), and 'Painting My Favorite Children's Song'(H), and the latter was 'Seeking for a Bluebird in My Mind'(L), and 'Making My Cherished Object' (M). Then I used the unique art expression technique per each theme, which were in sequence marbling, Korean paper art, combine painting, collage, imaginary painting, imaginary painting, play dough art, imaginary painting techniques. And I delivered to the students the scientific knowledge in terms of growing or manufacturing processes of materials used for making artworks. Prior to and after the processing this program, I surveyed about the students' ability of integrated thinking and emotional experience by 'Figure B Type' and 'Figure A Type' of The Torrance Tests of Creative Thinking, and took statistics with the resultant data. And I executed a paired t-test in order to verify the significance of mean difference in the result of investigation with those data. From the analyzed result according to the elements of creativity and the mean quotients of creativity, there showed a significant difference (t=3.47, p<.01) in 'fluency', and also a significant difference(t=3.59, p<.01) in 'creativity.' Judging from the statistic values of two fields such as the student's ability of integrated thinking and emotional experience, I estimate that over the majority of the students showed the enhancement in self-confident creative expression as well as higher interest and concern through this program. The result that I arranged and analyzed the making process of artworks, the photos of the resultant, etc. as such is as follows : Firstly, from this program being proceeded as art-centered STEAM class, the student's systematic problem-solving ability was improved in his ability of integrated thinking to transform the literary contents into artistic one. Secondly, the student obtained the emotional experience such as interest in the class, self-confidence, intellectual satisfaction, self-fulfillment, etc. through art-centered STEAM class using ten art expression techniques. Thirdly, the student's mind willing to cooperate, communicate with his friends, and care for them was ripened in the process of problem-solving. Fourth, the student's self-confidence was further instilled when presenting famous artists and their artworks in the introduction and finale of ten art expression techniques. Likewise, the statistic values on the fields of student's ability of integrated thinking and emotional experience illustrate that over the majority of the students showed improvement in the ability of creative expression with confidence as well as higher interest and concern upon this program.
The study examines how the environmental factors of store influence service brand personality and repurchase intention in the service environment. The service industry has been experiencing the intensified competition with the industry's continuous growth and the influence from rapid technological advancement. Under the circumstances, it has become ever more important for the brand competitiveness to be distinctively recognized against competition. A brand needs to be distinguished and differentiated from competing companies because they are all engaged in the similar environment of the service industry. The differentiation of brand achievement has become increasingly important to highlight certain brand functions to include emotional, self-expressive, and symbolic functions since the importance of such functions has been further emphasized in promoting consumption activities. That is the recent role of brand personality that has been emphasized in the service industry. In other words, customers now freely and actively express their personalities or egos in consumption activities, taking an important role in construction of a brand asset. Hence, the study suggests that it is necessary to disperse the recognition and acknowledgement that the maintenance of the existing customers contributes more to boost repurchase intention when it is compared to the efforts to create new customers, particularly in the service industry. Meanwhile, the store itself can offer a unique environment that may influence the consumer's purchase decision. Consumers interact with store environments in the process of,virtually, all household purchase they make (Sarel 1981). Thus, store environments may encourage customers to purchase. The roles that store environments play are to provide informational cues to customers about the store and goods and communicate messages to stimulate consumers' emotions. The store environments differentiate the store from competing stores and build a unique service brand personality. However, the existing studies related to brand in the service industry mostly concentrated on the relationship between the quality of service and customer satisfaction, and they are mostly generalized while the connective studies focused on brand personality. Such approaches show limitations and are insufficient to investigate on the relationship between store environment and brand personality in the service industry. Accordingly, the study intends to identify the level of contribution to the establishment of brand personality made by the store's physical environments that influence on the specific brand characteristics depending on the type of service. The study also intends to identify what kind of relationships with brand personality exists with brand personality while being influenced by store environments. In addition, the study intends to make meaningful suggestions to better direct marketing efforts by identifying whether a brand personality makes a positive influence to induce an intention for repurchase. For this study, the service industry is classified into four categories based on to the characteristics of service: experimental-emotional service, emotional -credible service, credible-functional service, and functional-experimental service. The type of business with the most frequent customer contact is determined for each service type and the enterprise with the highest brand value in each service sector based on the report made by the Korea Management Association. They are designated as the representative of each category. The selected representatives are a fast-food store (experimental-emotional service), a cinema house (emotional-credible service), a bank (credible-functional service), and discount store (functional-experimental service). The survey was conducted for the four selected brands to represent each service category among consumers who are experienced users of the designated stores in Seoul Metropolitan City and Gyeonggi province via written questionnaires in order to verify the suggested assumptions in the study. In particular, the survey adopted 15 scales, which represent each characteristic factor, among the 42 unique characteristics developed by Jennifer Aaker(1997) to assess the brand personality of each service brand. SPSS for Windows Release 12.0 and LISREL were used in the analysis of data verification. The methodology of the structural equation model was used for the study and the pivotal findings are as follows. 1) The environmental factors ware classified as design factors, ambient factors, and social factors. Therefore, the validity of measurement scale of Baker et al. (1994) was proved. 2) The service brand personalities were subdivided as sincerity, excitement, competence, sophistication, and ruggedness, which makes the use of the brand personality scales by Jennifer Aaker(1997) appropriate in the service industry as well. 3) One-way ANOVA analysis on the scales of store environment and service brand personality showed that there exist statistically significant differences in each service category. For example, the social factors were highest in discount stores, while the ambient factors and design factors were highest in fast-food stores. The discount stores were highest in the sincerity and excitement, while the highest point for banks was in the competence and ruggedness, and the highest point for fast-food stores was in the sophistication, The consumers will make a different respond to the physical environment of stores and service brand personality that are inherent to the corresponding service interface. Hence, the customers will make a different decision-making when dealing with different service categories. In this aspect, the relationships of variables in the proposed hypothesis appear to work in a different way depending on the exposed service category. 4) The store environment factors influenced on service brand personalities differently by category of service. The factors of store's physical environment are transferred to a brand and were verified to strengthen service brand personalities. In particular, the level of influence on the service brand personality by physical environment differs depending on service category or dimension, which indicates that there is a need to apply a different style of management to a different service category or dimension. It signifies that there needs to be a brand strategy established in order to positively influence the relationship with consumers by utilizing an appropriate brand personality factor depending on different characteristics by service category or dimension. 5) The service brand personalities influenced on the repurchase intention. Especially, the largest influence was made in the sophistication dimension of service brand personality scale; the unique and characteristically appropriate arrangement of physical environment will make customers stay in the service environment for a long time and will lead to give a positive influence on the repurchase intention. 6) The store environment factors influenced on the repurchase intention. Particularly, the largest influence was made on the social factors of store environment. The most intriguing finding is that the service factor among all other environment factors gives the biggest influence to the repurchase intention in most of all service types except fast-food stores. Such result indicates that the customers pay attention to how much the employees try to provide a quality service when they make an evaluation on the service brand. At the same time, it also indicates that the personal factor is directly transmitted to the construction of brand personality. The employees' attitude and behavior are the determinants to establish a service brand personality in the process of enhancing service interface. Hence, there should be a reinforced search for a method to efficiently manage the service staff who has a direct contact with customers in order to make an affirmative improvement of the customers' brand evaluation at the service interface. The findings suggest several managerial implications. 1) Results from the empirical study indicated that store environment factors have a strong positive impact on a service brand personality. To increase customers' repurchase intention of a service brand, the management is required to effectively manage store environment factors and create a friendly brand personality based on the corresponding service environment. 2) Mangers and researchers must understand and recognize that the store environment elements are important marketing tools, and that brand personality influences on consumers' repurchase intention. Based on such result of the study, a service brand could be utilized as an efficient measure to achieve a differentiation by enforcing the elements that are most influential among all other store environments for each service category. Therefore, brand personality established involving various store environments will further reinforce the relationship with customers through the elevated brand identification of which utilization to induce repurchase decision can be used as an entry barrier. 3) The study identified the store environment as a component of service brand personality for the store's effective communication with consumers. For this, all communication channels should be maintained with consistency and an integrated marketing communication should be executed to efficiently approach to a larger number of customers. Mangers and researchers must find strategies for aligning decisions about store environment elements with the retailers' marketing and store personality objectives. All ambient, design, and social factors need to be orchestrated so that consumers can take an appropriate store personality. In this study, the induced results from the previous studies were extended to the service industry so as to identify the customers' decision making process that leads to repurchase intention and a result similar to those of the previous studies. The findings suggested several theoretical and managerial implications. However, the situation that only one service brand served as the subject of analysis for each service category, and the situation that correlations among store environment elements were not identified, as well as the problem of representation in selection of samples should be considered and supplemented in the future when further studies are conducted. In addition, various antecedents and consequences of brand personality must be looked at in the aspect of the service environment for further research.
These experiments pertain to various factors influencing the quantitative characters of cocoon crops in summer and early autumn seasons. Initially, in order to establish the possible ways of the silkworm rearing more than three times a year in Korea, the author attempted to get further information about the various factors affecting the cocoon crop in every silkworm rearing season. The trials were conducted eleven times a year at four places for three years. The field trial was conducted with 19 typical sericultural farmers who had been surveyed. At the same time the author statistically analyzed the various factors in close relation to tile cocoon crop in autumn season. The effect of guidance on 40 sericultural farmers was analyzed, comparing higher level farmers with lower level farmers ; and the author surveyed 758 non-guided farmers near the guided farmers during both spring and autumn seasons. In addition, another trial on the seasonal change of leaf quality was attempted with artificial diets prepared with leaves grown in each season. It was found that related factors to cocoon crops in summer and early autumn seasons appeared to be leaf quality, and temperature for young and grown larvae. A 2
Introduction As consumers' purchase behavior change into a rational and practical direction, the discount store industry came to have keen competition along with rapid external growth. Therefore as a solution, distribution businesses are concentrating on developing PB(Private Brand) which can realize differentiation and profitability at the same time. And as improvement in customer loyalty beyond customer satisfaction is effective in surviving in an environment with keen competition, PB is being used as a strategic tool to improve customer loyalty. To improve loyalty among PB users, it is necessary to develop PB by examining properties of a customer group, first of all, quality level perceived by consumers should be met to obtain customer satisfaction and customer trust and consequently induce customer loyalty. To provide results of systematic analysis on relations between antecedents influenced perceived quality and variables affecting customer loyalty, this study proposed a research model based on causal relations verified in prior researches and set 16 hypotheses about relations among 9 theoretical variables. Data was collected from 400 adult customers residing in Seoul and the Metropolitan area and using large scale discount stores, among them, 375 copies were analyzed using SPSS 15.0 and Amos 7.0. The findings of the present study followed as; We ascertained that the higher company reputation, brand reputation, product experience and brand familiarity, the higher perceived quality. The study also examined the higher perceived quality, the higher customer satisfaction, customer trust and customer loyalty. The findings showed that the higher customer satisfaction and customer trust, the higher customer loyalty. As for moderating effects between PB and NB in terms of influences of perceived quality factors on perceived quality, we can ascertain that PB was higher than NB in the influences of company reputation on perceived quality while NB was higher than PB in the influences of brand reputation and brand familiarity on perceived quality. These results of empirical analysis will be useful for those concerned to do marketing activities based on a clearer understanding of antecedents and consecutive factors influenced perceived quality. At last, discussions about academical and managerial implications in these results, we suggested the limitations of this study and the future research directions. Research Model and Hypotheses Test After analyzing if antecedent variables having influence on perceived quality shows any difference between PB and NB in terms of their influences on them, the relation between variables that have influence on customer loyalty was determined as Figure 1. We established 16 hypotheses to test and hypotheses are as follows; H1-1: Perceived price has a positive effect on perceived quality. H1-2: It is expected that PB and NB would have different influence in terms of perceived price on perceived quality. H2-1: Company reputation has a positive effect on perceived quality. H2-2: It is expected that PB and NB would have different influence in terms of company reputation on perceived quality. H3-1: Brand reputation has a positive effect on perceived quality. H3-2: It is expected that PB and NB would have different influence in terms of brand reputation on perceived quality. H4-1: Product experience has a positive effect on perceived quality. H4-2: It is expected that PB and NB would have different influence in terms of product experience on perceived quality. H5-1: Brand familiarity has a positive effect on perceived quality. H5-2: It is expected that PB and NB would have different influence in terms of brand familiarity on perceived quality. H6: Perceived quality has a positive effect on customer satisfaction. H7: Perceived quality has a positive effect on customer trust. H8: Perceived quality has a positive effect on customer loyalty. H9: Customer satisfaction has a positive effect on customer trust. H10: Customer satisfaction has a positive effect on customer loyalty. H11: Customer trust has a positive effect on customer loyalty. Results from analyzing main effects of research model is shown as